Interpretable XGBoost-SHAP Model for Arrhythmic Heartbeat Classification

With the rising incidence of cardiovascular diseases, efficient arrhythmia detection from Electrocardiogram signals is crucial.Traditional Machine Learning and Deep Learning methods for automatic ECG analysis have demonstrated promising results with high accuracy but often suffer from a lack of interpretability and challenges in correctly identifying similar beats and detecting sporadic abnormalities.We propose a novel heartbeat arrhythmia classification model that combines eXtreme Gradient Boosting with Shapley Additive explanations.Our model extracted features from single heartbeat, emphasizing the characteristics crucial for differentiating between similar heartbeat.By addressing data imbalance and selecting features, we achieved 98.91% accuracy in the 5-class classification problem devoted by the Association for the Advancement of Medical Instrumentation.The contribution of our study is to demonstrate the feasibility of directly classifying arrhythmias from single heartbeats, and incorporate interpretability into the heartbeat classification process, enabling clinicians to better understand model decision.